Runpod Serverless Flex pricing: why VRAM alone is the wrong comparison
Runpod's Flex tiers range from $0.58/hour 16GB classes to high-end B300 capacity. The useful decision is model fit, hardware class, and measured cost per job—not VRAM alone.
← Back to GPU Cloud
✓ VERIFIED
Nebius · GPU Cloud · GPU Instance
Nebius NVIDIA HGX B200 — On-demand
Nebius NVIDIA B200 on-demand costs USD 8.50 per GPU-hour for one GPU with 180 GB VRAM; the listed configuration includes 20 vCPUs and 224 GB RAM. The platform is documented in us-central1; me-west1, with storage charged separately.
CURRENT PRICE$8.50 / hrNative listed value
Fit & constraints
Fit & constraints
Use-case fit and limitations from the existing resource record.
AVAILABILITY
Available
Material changes only
Price intelligence
Recorded price-change events provide the comparison; no synthetic market reference is created.
Previous$7.15Recorded history
Current$8.50Same metric · same currency
Recorded change+19%USD/hour
| Observed at | Change type | Previous | Current | Metric | Evidence |
|---|---|---|---|---|---|
| 2026-10-01 | PRICE RISE | $7.15 | $8.50 | USD/hour | Source ↗ |
Resource facts
Key specs
Non-price resource facts only; pricing, history, and evidence stay in their own sections.
GPU MODELNVIDIA HGX B200
GPU COUNT1
VRAM180 GB
VCPU20
RAM224 GB
LOCATIONus-central1; me-west1
Trust layer
Verified evidence
Decision visuals remain traceable to the existing source and verification record.
Independent ranking · native prices · evidence-linked · commercial relationships isolated from scoring and publication.
WATCH